{"name":"MacOS-MCP: Lightweight MCP Server for AI Automation on macOS","description":"MacOS-MCP is a lightweight, open-source Model Context Protocol server designed to bridge AI agents with the macOS operating system. It enables seamless automation of macOS tasks such as file navigation, application control, and UI interaction through large language models, without requiring computer vision or specialized setups. This project provides a robust toolkit for AI-driven desktop automation.","github":"https://github.com/CursorTouch/MacOS-MCP","url":"https://osrepos.com/repo/cursortouch-macos-mcp","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/cursortouch-macos-mcp","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/cursortouch-macos-mcp.md","json":"https://osrepos.com/repo/cursortouch-macos-mcp.json","topics":["macos","mcp-server","python","ai-automation","llm-tools","desktop-automation","open-source"],"keywords":["macos","mcp-server","python","ai-automation","llm-tools","desktop-automation","open-source"],"stars":null,"summary":"MacOS-MCP is a lightweight, open-source Model Context Protocol server designed to bridge AI agents with the macOS operating system. It enables seamless automation of macOS tasks such as file navigation, application control, and UI interaction through large language models, without requiring computer vision or specialized setups. This project provides a robust toolkit for AI-driven desktop automation.","content":"## Introduction\n\nMacOS-MCP is an open-source, lightweight Model Context Protocol (MCP) server that empowers AI agents to interact seamlessly with the macOS operating system. It acts as a bridge, allowing large language models (LLMs) to automate a wide range of macOS tasks, including file navigation, application control, UI interaction, browser automation, and general system operations. Unlike many traditional automation tools, MacOS-MCP leverages the native macOS Accessibility API, eliminating the need for computer vision, fine-tuned models, or specialized setups, making it compatible with any LLM.\n\n## Installation\n\nGetting started with MacOS-MCP involves a few prerequisites and simple steps.\n\n### Prerequisites\n\n-   **Python**: Version 3.11 or later\n-   **UV Package Manager**: Install with `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh | sh`\n-   **macOS**: Version 12 (Monterey) or later\n-   **Accessibility Permissions**: Essential for UI interaction\n\n### Quick Start\n\nYou can run the server directly from your terminal:\n\nshell\nuvx macos-mcp\n\n\nFor network access, use specific transport options:\n\nshell\nuvx macos-mcp --transport sse --host localhost --port 8000\n# Or for production-ready HTTP streaming\nuvx macos-mcp --transport streamable-http --host localhost --port 8000\n\n\nTo install it as a background service that starts at login:\n\nshell\nmacos-mcp install\n\n\n### Grant Required Permissions\n\nMacOS-MCP requires **Accessibility** and **Screen Recording** permissions. Navigate to **System Settings ? Privacy & Security** and grant access to your terminal application, Python, and UV under both **Accessibility** and **Screen Recording**. The server can also prompt for Accessibility permissions on startup.\n\n## Examples\n\nMacOS-MCP is designed for integration with various AI agent platforms. Here are a couple of examples demonstrating its use:\n\n### Pi Agent Integration\n\nMacOS-MCP can be installed as a Pi package, exposing convenient Pi tools that wrap the existing macOS-MCP functionalities.\n\n**One-line global setup:**\n\nshell\npi install git:github.com/CursorTouch/MacOS-MCP\n\n\nAfter installation, restart Pi or run `/reload`.\n\nThe extension exposes tools like `mac_snapshot` (to read UI state), `mac_app` (to manage applications), `mac_click` (to click coordinates), `mac_type` (to type text), `mac_shortcut` (to run keyboard shortcuts), and `mac_scroll` (to scroll). The recommended workflow is to call `mac_snapshot` first and then use its returned coordinates with other tools.\n\n### Tau Coding Agent Integration\n\nThis repository includes a project-local Tau extension that starts the macOS-MCP server and exposes Tau-native tools.\n\n**Local checkout setup:**\n\nshell\ngit clone https://github.com/CursorTouch/MacOS-MCP.git\ncd MacOS-MCP\nuv sync\ntau\n\n\nTau auto-discovers project extensions. Similar to Pi, it provides tools like `mac_snapshot`, `mac_app`, `mac_click`, `mac_type`, `mac_shortcut`, and `mac_scroll` for interacting with macOS.\n\nOther integrations include Claude Desktop, Gemini CLI, and Claude Code, all configurable via their respective MCP server settings.\n\n## Why Use MacOS-MCP?\n\nMacOS-MCP offers several compelling advantages for AI-driven macOS automation:\n\n*   **LLM Agnostic**: Works seamlessly with any LLM, including Claude, GPT, and Gemini, without requiring specialized models or computer vision.\n*   **Native macOS Integration**: Interacts directly with macOS UI elements using the Accessibility API, allowing for robust control over applications, windows, and user input.\n*   **Rich Toolset**: Provides a comprehensive suite of tools for keyboard/mouse operations, window management, UI state capture, interactive element extraction, and AppleScript execution.\n*   **Lightweight and Open-Source**: Minimal dependencies, full source code available under the MIT license, ensuring easy setup and customizability.\n*   **Smart Context Awareness**: Intelligently detects application states and scans system UI elements like the menu bar, dock, and desktop.\n*   **Security Features**: Includes options for authentication (Bearer token), IP allowlisting, TLS/HTTPS, and OAuth 2.0 + PKCE, allowing for secure deployment in network environments.\n\n## Links\n\nFor more detailed information, contributions, or to report issues, please refer to the official repository and documentation:\n\n*   **GitHub Repository**: [https://github.com/CursorTouch/MacOS-MCP](https://github.com/CursorTouch/MacOS-MCP){:target=\"_blank\"}\n*   **License (MIT)**: [https://github.com/CursorTouch/MacOS-MCP/blob/main/LICENSE](https://github.com/CursorTouch/MacOS-MCP/blob/main/LICENSE){:target=\"_blank\"}\n*   **Contributing Guide**: [https://github.com/CursorTouch/MacOS-MCP/blob/main/CONTRIBUTING.md](https://github.com/CursorTouch/MacOS-MCP/blob/main/CONTRIBUTING.md){:target=\"_blank\"}\n*   **Security Information**: [https://github.com/CursorTouch/MacOS-MCP/blob/main/SECURITY.md](https://github.com/CursorTouch/MacOS-MCP/blob/main/SECURITY.md){:target=\"_blank\"}","metrics":{"detailViews":1,"githubClicks":0},"dates":{"published":null,"modified":"2026-07-08T15:34:37.000Z"}}